INDEX

Explanations

locations and law enforcement related terms

oai_token-act-pair · gpt-3.5-turbo

specific references to law enforcement agencies and personnel

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 embr

-0.84

 UNESCO

-0.81

olkien

-0.80

TPP

-0.75

 trillions

-0.75

 prestige

-0.75

 stagnation

-0.74

kefeller

-0.74

 renegoti

-0.74

 Tolkien

-0.73

POSITIVE LOGITS

 detectives

1.67

Police

1.66

 Police

1.66

 police

1.62

police

1.61

 Detect

1.46

 Investigators

1.42

Detect

1.40

Investigators

1.40

Officers

1.38

Activations Density 0.440%

locations and law enforcement related terms

specific references to law enforcement agencies and personnel

No Comments

No Known Activations